Commit graph

11 commits

Author SHA1 Message Date
Scott
6f4bd814b8
fix(coding-agent): allow provider-scoped custom model ids (#1759) 2026-03-03 14:20:49 +01:00
Mario Zechner
7364696ae6 fix(coding-agent): prefer provider/model split over gateway model id matching
When resolving --model zai/glm-5, the resolver now correctly interprets
'zai' as the provider and 'glm-5' as the model id, rather than matching
a vercel-ai-gateway model whose id is literally 'zai/glm-5'.

If the provider/model split fails to find a match, falls back to raw id
matching to still support OpenRouter-style ids like 'openai/gpt-4o:extended'.
2026-02-22 14:40:36 +01:00
Mario Zechner
4793f7c92d fix(coding-agent): make resolveCliModel sync, update docs and changelog 2026-02-12 19:04:51 +01:00
Armin Ronacher
56342258e1 fix(coding-agent): honor --model selection, thinking, and --api-key 2026-02-12 18:58:45 +01:00
Mario Zechner
61fe132946 fix(coding-agent): stabilize pinned git parsing and model default test 2026-02-05 21:43:27 +01:00
Mario Zechner
19f3c23f6d Fix PR #689: Add changelog attribution, coding-agent changelog, fix test types, add provider to test suites
- Fix ai/CHANGELOG.md: add PR link and author attribution
- Add coding-agent/CHANGELOG.md entry for vercel-ai-gateway provider
- Fix model-resolver.test.ts: use anthropic-messages API type to match generated models
- Add vercel-ai-gateway to test suites: tokens, abort, empty, context-overflow, unicode-surrogate, tool-call-without-result, image-tool-result, total-tokens, image-limits
2026-01-13 16:46:00 +01:00
Timo Lins
65eb738c90 Rename to vercel-ai-gateway for clarity 2026-01-13 16:42:34 +01:00
Timo Lins
164a69a601 Add Vercel AI Gateway support 2026-01-13 16:42:34 +01:00
Fero
cbd3a8cb87
fix: use defaultThinkingLevel from settings when enabledModels lacks explicit suffix (#540)
When enabledModels is configured without thinking level suffixes (e.g.,
'claude-opus-4-5' instead of 'claude-opus-4-5:high'), the scoped model's
default 'off' thinking level was overriding defaultThinkingLevel from
settings.

Now thinkingLevel in ScopedModel is optional (undefined means 'not
explicitly specified'). When passing to SDK, undefined values are filled
with defaultThinkingLevel from settings.
2026-01-07 18:11:03 +01:00
Mario Zechner
d6283f99dc refactor(hooks): split session events into individual typed events
Major changes:
- Replace monolithic SessionEvent with reason discriminator with individual
  event types: session_start, session_before_switch, session_switch,
  session_before_new, session_new, session_before_branch, session_branch,
  session_before_compact, session_compact, session_shutdown
- Each event has dedicated result type (SessionBeforeSwitchResult, etc.)
- HookHandler type now allows bare return statements (void in return type)
- HookAPI.on() has proper overloads for each event with correct typing

Additional fixes:
- AgentSession now always subscribes to agent in constructor (was only
  subscribing when external subscribe() called, breaking internal handlers)
- Standardize on undefined over null throughout codebase
- HookUIContext methods return undefined instead of null
- SessionManager methods return undefined instead of null
- Simplify hook exports to 'export type * from types.js'
- Add detailed JSDoc for skipConversationRestore vs cancel
- Fix createBranchedSession to rebuild index in persist mode
- newSession() now returns the session file path

Updated all example hooks, tests, and emission sites to use new event types.
2025-12-30 22:42:22 +01:00
Aliou Diallo
9a7863fc98
fix(coding-agent): handle OpenRouter models with colons in IDs (#242) 2025-12-19 15:26:12 +01:00